Jango
Test multi-user apps with AI agents that act like real users
Start new thread

Jango - Test multi-user apps with AI agents that act like real users

by
•
Jango lets you test the parts of your app that need more than one person. It gives your app a group of AI users, each with its own browser, account, goals and memory. Point Jango at your dev URL and watch them sign in and interact with each other in real time. Direct them, join in as yourself, or take control of any user's screen. At the end you get a report with actions, errors and screenshots. Use your own AI key or Jango's managed AI. Available on Mac.

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt 👋 I built Jango because testing multi-user features alone is painful. You end up juggling five browser windows and fake accounts. Jango runs a group of AI users, each with their own login and memory, so you can see how your app holds up when several people use it at once. I'd love your feedback!
Vercel
Vercel Day
Which Vercel product did you use? What new capability did it give your team, and how did that shape the product you launched?
Maker
Vercel hosting, with preview deployments and a custom domain. Jango is a Mac app, but a desktop product still needs a fast, trustworthy home on the web: the landing page, download links, and the email-confirmation and password-reset pages the desktop sign-up flow sends people to. Vercel gave me, a solo founder, that whole web surface with no infrastructure to run. Every push gets a preview URL, so I could check copy, pricing and download links before they went live, and connecting usejango.com took minutes. That shaped the launch: I could keep the desktop app focused on running browsers and AI agents locally, and treat the website as something I iterate on daily alongside the product instead of a separate project. It also meant I could ship the prerendered, SEO-friendly marketing pages and the account flows at the same time as the 1.1 release.

the memory-across-sessions detail is what makes this more than a scripted test runner. one thing I'm curious about, since the agents each have their own goals and can act in real time, do you ever get genuine race conditions out of it, like two agents both grabbing the last item in a cart or both trying to claim the same slot at the same instant, or does it stay mostly sequential in practice even with multiple browsers running